© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68878
    Prev
    Next
    INDEX
    Explanations

    achieve acceptable level

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects verbs (and related nouns) that express sustaining, maintaining, or providing some ongoing service, state, or functionality.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    馒头
    -1.03
    dsquared
    -1.02
     identificado
    -1.01
    最初から
    -0.96
     estableció
    -0.92
    を高
    -0.92
    tative
    -0.90
     calentamiento
    -0.90
     contribution
    -0.89
     Flücht
    -0.89
    POSITIVE LOGITS
    겟
    1.04
    ureusement
    1.02
    ícias
    1.02
    ********/
    0.99
     because
    0.98
     desesper
    0.98
    chaub
    0.97
    acceptable
    0.96
    ജ
    0.95
    Attempt
    0.94
    Activations Density 0.050%

    No Known Activations